DeepSeek-V3.2 vs DeepSeek-V4-Flash
DeepSeek vs DeepSeek — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 87.1)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $0.25 per 1M input)
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V3.2 | DeepSeek-V4-Flash | |
|---|---|---|
| Intelligence index | 87.1 | 89.4 |
| Developer | DeepSeek | DeepSeek |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 131,072 tokens | 1,048,576 tokens |
| Input price | $0.25 / 1M | $0.10 / 1M |
| Output price | $0.38 / 1M | $0.20 / 1M |
| Speed | — | 109 tok/s |
| Released | December 1, 2025 | April 24, 2026 |
| Parameters | 671B (37B active) | 284B (13B active) |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V3.2
DeepSeek-V4-Flash
GPQA Diamond
84
89.4
Humanity’s Last Exam
22.2
32.1